agent-browser

Automate browser navigation, form filling, and data extraction via CLI.

42|5|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/kazdenc/builder-skills --skill agent-browser-kazdenc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/kazdenc/builder-skills/tree/main/.claude/skills/tools/agent-browser
Command: npx skills add https://github.com/kazdenc/builder-skills --skill agent-browser-kazdenc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables AI agents to programmatically interact with web browsers, automating tasks like navigating websites, filling forms, clicking buttons, and extracting data, which is crucial for web automation and testing.

Core Features & Use Cases

  • Web Navigation: Open URLs, navigate pages, and manage browser tabs.
  • Form Interaction: Fill text fields, select dropdown options, check boxes, and submit forms.
  • Data Extraction: Scrape text content, element attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs for documentation or analysis.
  • Use Case: Automate the process of logging into a web application, filling out a complex multi-step form, and then extracting the confirmation details.

Quick Start

Use the agent-browser skill to open the website 'https://example.com' and take a screenshot named 'example.png'.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser automation tasks for an AI agent via CLI?

Browser automation for AI agents is handled via a command-line interface that enables programmatic website interaction, supporting navigation, form filling, and data scraping. It utilizes Playwright to ensure cross-browser compatibility during these automated interactions.

Can I use Playwright to automate form filling and web scraping with AI agents?

Yes, Playwright supports automating form filling and web scraping for AI agents. The interface allows agents to fill text fields, select dropdown options, extract structured data, and submit forms programmatically across different browsers.

What is the best way to capture full-page screenshots and generate PDFs during web scraping?

Capturing full-page screenshots and generating PDFs during web scraping is accomplished through the browser automation CLI. It allows AI agents to capture visual documentation or save pages as PDFs directly from the automated browsing session.

Does browser automation support session persistence and authentication flows?

Yes, browser automation supports session persistence and authentication flows. This allows AI agents to log into web applications, maintain authenticated states across interactions, and automate complex multi-step form submissions.

Do I need any dependencies to use this browser automation CLI for cross-browser compatibility?

No external dependencies are required to use this browser automation CLI. It operates independently while utilizing Playwright internally to provide cross-browser compatibility for navigation, form filling, and data extraction tasks.